R语言学习 - 基础概念和矩阵操作

R基本语法

获取帮助文档，查看命令或函数的使用方法、事例或适用范围

>>> ?command
>>> ??command #深度搜索或模糊搜索此命令




    


>>> example(command) #得到命令的例子

R中的变量

> # 数字变量
> a 10
> a
[1] 10
> 
> # 字符串变量
> a "abc"
> a
[1] "abc"
> 
> # 逻辑变量
> a TRUE
> 
> a
[1] TRUE
> 
> b T
> 
> b
[1] TRUE
> 
> d FALSE
> 
> d
[1] FALSE
> # 向量
> 
> a "logical", length=5)
> a
[1] FALSE FALSE FALSE FALSE FALSE
> 
> a 1,2,3,4)
# 判断一个变量是不是vector
> is.vector(a)
[1] TRUE
> 
> # 矩阵
> 
> a 1:20,nrow=5,ncol=4,byrow=T)
> a
     [,1] [,2] [,3] [,4]
[1,]    1    2    3    4
[2,]    5    6    7    8
[3,]    9   10   11   12
[4,]   13   14   15   16
[5,]   17   18   19   20
> 
> is.matrix(a)
[1] TRUE
> 
> dim(a) #查看或设置数组的维度向量
[1] 5 4
> 
> # 错误的用法
> dim(a) 4,4)
Error in dim(a) 4, 4) : dims [product 16]与对象长度[20]不匹配
> 
> # 正确的用法
> a 1:20
> dim(a) 5,4) #转换向量为矩阵
> a
     [,1] [,2] [,3] [,4]
[1,]    1    6   11   16
[2,]    2    7   12   17
[3,]    3    8   13   18
[4,]    4    9   14   19
[5,]    5   10   15   20
> 
> print(paste("矩阵a的行数", nrow(a)))
[1] "矩阵a的行数 5"
> print(paste("矩阵a的列数", ncol(a)))
[1] "矩阵a的列数 4"
> 
> #查看或设置行列名
> rownames(a)
NULL
> rownames(a) 'a','b','c','d','e')
> a
  [,1] [,2] [,3] [,4]
a    1    6   11   16
b    2    7   12   17
c    3    8   13   18
d    4    9   14   19
e    5   10   15   20

# R中获取一系列的字母
> letters[1:4]
[1] "a" "b" "c" "d"
> colnames(a) 1:4]
> a
  a  b  c  d
a 1  6 11 16
b 2  7 12 17
c 3  8 13 18
d 4  9 14 19
e 5 10 15 20
> 

# is系列和as系列函数用来判断变量的属性和转换变量的属性
# 矩阵转换为data.frame
> is.character(a)
[1] FALSE
> is.numeric(a)
[1] TRUE
> is.matrix(a)
[1] TRUE
> is.data.frame(a)
[1] FALSE
> is.data.frame(as.data.frame(a))
[1] TRUE

R中矩阵运算

# 数据产生
# rnorm(n, mean = 0, sd = 1) 正态分布的随机数
# runif(n, min = 0, max = 1) 平均分布的随机数
# rep(1,5) 把1重复5次
# scale(1:5) 标准化数据
> a 5), rnorm(5,1), runif(5), runif(5,-1,1), 1:5, rep(0,5), c(2,10,11,13,4), scale(1:5)[1:5])
> a
 [1] -0.41253556  0.12192929 -0.47635888 -0.97171653




    
  1.09162243  1.87789657
 [7] -0.11717937  2.92953522  1.33836620 -0.03269026  0.87540920  0.13005744
[13]  0.11900686  0.76663940  0.28407356 -0.91251181  0.17997973  0.50452258
[19]  0.25961316 -0.58052230  1.00000000  2.00000000  3.00000000  4.00000000
[25]  5.00000000  0.00000000  0.00000000  0.00000000  0.00000000  0.00000000
[31]  2.00000000 10.00000000 11.00000000 13.00000000  4.00000000 -1.26491106
[37] -0.63245553  0.00000000  0.63245553  1.26491106
> a 5, byrow=T)
> a
           [,1]       [,2]       [,3]       [,4]        [,5]
[1,] -0.4125356  0.1219293 -0.4763589 -0.9717165  1.09162243
[2,]  1.8778966 -0.1171794  2.9295352  1.3383662 -0.03269026
[3,]  0.8754092  0.1300574  0.1190069  0.7666394  0.28407356
[4,] -0.9125118  0.1799797  0.5045226  0.2596132 -0.58052230
[5,]  1.0000000  2.0000000  3.0000000  4.0000000  5.00000000
[6,]  0.0000000  0.0000000  0.0000000  0.0000000  0.00000000
[7,]  2.0000000 10.0000000 11.0000000 13.0000000  4.00000000
[8,] -1.2649111 -0.6324555  0.0000000  0.6324555  1.26491106

# 求行的加和
> rowSums(a)
[1] -0.6470593  5.9959284  2.1751865 -0.5489186 15.0000000  0.0000000 40.0000000
[8]  0.0000000

## 注意检查括号的配对
> a 0,]
错误: 意外的']' in "a 

# 去除全部为0的行
> a 0,]

# 另外一种方式去除全部为0的行
> #a[rowSums(a==0)
> a
           [,1]       [,2]       [,3]       [,4]        [,5]
[1,] -0.4125356  0.1219293 -0.4763589 -0.9717165  1.09162243
[2,]  1.8778966 -0.1171794  2.9295352  1.3383662 -0.03269026
[3,]  0.8754092  0.1300574  0.1190069  0.7666394  0.28407356
[4,] -0.9125118  0.1799797  0.5045226  0.2596132 -0.58052230
[5,]  1.0000000  2.0000000  3.0000000  4.0000000  5.00000000
[6,]  2.0000000 10.0000000 11.0000000 13.0000000  4.00000000
[7,] -1.2649111 -0.6324555  0.0000000  0.6324555  1.26491106

# 矩阵运算，R默认针对整个数据进行常见运算

# 所有值都乘以2

> a * 2
           [,1]       [,2]       [,3]       [,4]        [,5]
[1,] -0.8250711  0.2438586 -0.9527178 -1.9434331  2.18324487
[2,]  3.7557931 -0.2343587  5.8590704  2.6767324 -0.06538051
[3,]  1.7508184  0.2601149  0.2380137  1.5332788  0.56814712
[4,] -1.8250236  0.3599595  1.0090452  0.5192263 -1.16104460
[5,]  2.0000000  4.0000000  6.0000000  8.0000000 10.00000000
[6,]  4.0000000 20.0000000 22.0000000 26.0000000  8.00000000
[7,] -2.5298221 -1.2649111  0.0000000  1.2649111  2.52982213

# 所有值取绝对值，再取对数 （取对数前一般加一个数避免对0或负值取对数）
> log2(abs(a)+1)
          [,1]      [,2]      [,3]      [,4]      [,5]
[1,] 0.4982872 0.1659818 0.5620435 0.9794522 1.0646224
[2,] 1.5250147 0.1598608 1.9743587 1.2255009 0.0464076
[3,] 0.9072054 0.1763961 0.1622189 0.8210076 0.3607278
[4,] 0.9354687 0.2387621 0.5893058 0.3329807 0.6604014
[5,] 1.0000000 1.5849625 2.0000000 2.3219281 2.5849625
[6,] 1.5849625 3.4594316 3.5849625 3.8073549 2.3219281
[7,] 1.1794544 0.7070437 0.0000000 0.7070437 1.1794544

# 取出最大值、最小值、行数、列数
> max(a)
[1] 13
> min(a)
[1] -1.264911
> nrow(a)
[1] 7
> ncol(a)
[1] 5

# 增加一列或一行
# cbind: column bind
> cbind(a, 1:7)
           [,1]       [,2]       [,3]       [,4]        [,5] [,6]
[1,] -0.4125356  0.1219293 -0.4763589 -0.9717165  1.09162243    1
[2,]  1.8778966 -0.1171794  2.9295352  1.3383662 -0.03269026    2
[3,]  0.8754092  0.1300574  0.1190069  0.7666394  0.28407356    3
[4,] -0.9125118  0.1799797  0.5045226  0.2596132 -0.58052230    4
[5,]  1.0000000  2.0000000  3.0000000  4.0000000  5.00000000    5
[6,]  2.0000000 10.0000000 11.0000000 13.0000000  4.00000000    6
[7,] -1.2649111 -0.6324555  0.0000000  0.6324555  1.26491106    7
> cbind(a, seven=1:7)
                                                             seven
[1,] -0.4125356  0.1219293 -0.4763589 -0.9717165  1.09162243     1
[2,]  1.8778966 -0.1171794  2.9295352  1.3383662 -0.03269026     2
[3,]  0.8754092  0.1300574  0.1190069  0.7666394  0.28407356     3
[4,] -0.9125118  0.1799797  0.5045226  0.2596132 -0.58052230     4
[5,]  1.0000000  2.0000000  3.0000000  4.0000000  5.00000000     5
[6,]  2.0000000 10.0000000 11.0000000 13.0000000  4.00000000     6
[7,] -1.2649111 -0.6324555  0.0000000  0.6324555  1.26491106     7

# rbind: row bind
> rbind(a,1:5)
           [,1]       [,2]       [,3]       [,4]        [,5]
[1,] -0.4125356  0.1219293 -0.4763589 -0.9717165  1.09162243
[2,]  1.8778966 -0.1171794  2.9295352  1.3383662 -0.03269026
[3,]  0.8754092  0.1300574  0.1190069  0.7666394  0.28407356
[4,] -0.9125118  0.1799797  0.5045226  0.2596132 -0.58052230
[5,]  1.0000000  2.0000000  3.0000000  4.0000000  5.00000000
[6,]  2.0000000 10.0000000 11.0000000 13.0000000  4.00000000
[7,] -1.2649111 -0.6324555  0.0000000  0.6324555  1.26491106
[8,]  1.0000000  2.0000000  3.0000000  4.0000000  5.00000000

# 计算每一行的mad (中值绝对偏差，一般认为比方差的鲁棒性更强，更少受异常值的影响，更能反映数据间的差异)
> apply(a,1,mad)
[1] 0.7923976 2.0327283 0.2447279 0.4811672 1.4826000 4.4478000 0.9376786